Detecting Smartwatch-Based Behavior Change in Response to a Multi-Domain Brain Health Intervention
Authors:
Open Access
- 7 April 2022
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing for Healthcare
- Vol. 3 (3) , 1-18
Abstract
In this study, we introduce and validate a computational method to detect lifestyle change that occurs in response to a multi-domain healthy brain aging intervention. To detect behavior change, digital behavior markers are extracted from smartwatch sensor data and a permutation-based change detection algorithm quantifies the change in marker-based behavior from a pre-intervention, 1-week baseline. To validate the method, we verify that changes are successfully detected from synthetic data with known pattern differences. Next, we employ this method to detect overall behavior change forn= 28 brain health intervention subjects andn= 17 age-matched control subjects. For these individuals, we observe a monotonic increase in behavior change from the baseline week with a slope of 0.7460 for the intervention group and a slope of 0.0230 for the control group. Finally, we utilize a random forest algorithm to perform leave-one-subject-out prediction of intervention versus control subjects based on digital marker delta values. The random forest predicts whether the subject is in the intervention or control group with an accuracy of 0.87. This work has implications for capturing objective, continuous data to inform our understanding of intervention adoption and impact.Keywords
Funding Information
- National Institutes of Health (R01EB009675 and R25AG046114)
- National Science Foundation (1954372)
This publication has 63 references indexed in Scilit:
- Cognitive Rehabilitation Multi-family Group Intervention for Individuals with Mild Cognitive Impairment and Their Care-PartnersJournal of the International Neuropsychological Society, 2014
- Potential for primary prevention of Alzheimer's disease: an analysis of population-based dataThe Lancet Neurology, 2014
- Multiple-Change-Point Detection for High Dimensional Time Series via Sparsified Binary SegmentationJournal of the Royal Statistical Society Series B: Statistical Methodology, 2014
- Mining GPS data for mobility patterns: A surveyPervasive and Mobile Computing, 2014
- Window Size Impact in Human Activity RecognitionSensors, 2014
- A tutorial on human activity recognition using body-worn inertial sensorsACM Computing Surveys, 2014
- Change-point detection in time-series data by relative density-ratio estimationNeural Networks, 2013
- Brain Health Knowledge in Community-Dwelling Older AdultsEducational Gerontology, 2012
- Social Engagement and Health in Younger, Older, and Oldest-Old Adults in the Louisiana Healthy Aging StudyJournal of Applied Gerontology, 2011
- Activities of Daily Living Are Associated With Older Adult Cognitive StatusJournal of Applied Gerontology, 2011